low-resource-machine-translation

NLP for human. A fast and easy-to-use natural language processing (NLP) toolkit, satisfying your imagination about NLP.

Fast + Non-Autoregressive Grammatical Error Correction using BERT. Code and Pre-trained models for paper "Parallel Iterative Edit Models for Local Sequence Transduction": www.aclweb.org/anthology/D19-1435.pdf (EMNLP-IJCNLP 2019)

ColBERT humor dataset for the task of humor detection, containing 200,000 jokes/news

Electra pre-trained model using Vietnamese corpus

Open-source benchmark datasets and pretrained transformer models in the Filipino language.

Implementation of ICLR 21 paper: Probing BERT in Hyperbolic Spaces

Speech synthesis (TTS) in low-resource languages by training from scratch with Fastpitch and fine-tuning with HifiGan

Bilingual term extractor

NLP pipelines for Tagalog using spaCy

Fast and memory-efficient library for WordPiece tokenization as it is used by BERT.